© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123516
    Prev
    Next
    INDEX
    Explanations

    Covent Garden, Soho, Bloomsbury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bluza
    -1.75
    wendige
    -1.56
    ANIEL
    -1.55
     betreffende
    -1.53
    ꪔ
    -1.52
    
    -1.51
    продам
    -1.48
    (^_^
    -1.46
     eléct
    -1.46
    🤕
    -1.45
    POSITIVE LOGITS
    ↵
    2.05
     B
    1.73
     w
    1.69
     From
    1.65
    </i>
    1.59
     /
    1.58
     ,
    1.56
    as
    1.55
    !!!
    1.55
    на
    1.54
    Activations Density 0.026%

    No Known Activations